{"id":"https://openalex.org/W7220919905","doi":"https://doi.org/10.1109/cvprf71909.2026.00109","title":"AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models","display_name":"AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7220919905","doi":"https://doi.org/10.1109/cvprf71909.2026.00109"},"language":"en","primary_location":{"id":"doi:10.1109/cvprf71909.2026.00109","doi":"https://doi.org/10.1109/cvprf71909.2026.00109","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/cvprf71909.2026.00109","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025994300","display_name":"Tianyi Yan","orcid":"https://orcid.org/0000-0003-3685-2566","observed_orcids":["https://orcid.org/0000-0003-3685-2566"]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tianyi Yan","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081233515","display_name":"Tao Tang","orcid":"https://orcid.org/0000-0001-8526-220X","observed_orcids":["https://orcid.org/0000-0001-8526-220X"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Tang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007286889","display_name":"Xingtai Gui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Xingtai Gui","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159277567","display_name":"Yongkang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Li","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061351647","display_name":"Jiasen Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiasen Zheng","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055500263","display_name":"Weiyao Huang","orcid":"https://orcid.org/0009-0004-9213-2744","observed_orcids":["https://orcid.org/0009-0004-9213-2744"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyao Huang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086548564","display_name":"Lingdong Kong","orcid":"https://orcid.org/0000-0003-3884-2185","observed_orcids":["https://orcid.org/0000-0003-3884-2185"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lingdong Kong","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058329224","display_name":"Wencheng Han","orcid":"https://orcid.org/0000-0002-1452-9832","observed_orcids":["https://orcid.org/0000-0002-1452-9832"]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Wencheng Han","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159257117","display_name":"Xia Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Zhou","raw_affiliation_strings":["Li Auto Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159272700","display_name":"Xueyang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyang Zhang","raw_affiliation_strings":["Li Auto Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120696887","display_name":"Yifei Zhan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Zhan","raw_affiliation_strings":["Li Auto Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746290","display_name":"Kun Zhan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhan","raw_affiliation_strings":["Li Auto Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159278833","display_name":"Cheng-Zhong Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Cheng-zhong Xu","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159275257","display_name":"Jianbing Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jianbing Shen","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68077221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.053599998354911804,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.8320000171661377},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.800000011920929},{"id":"https://openalex.org/keywords/optimism-bias","display_name":"optimism bias","score":0.7059999704360962},{"id":"https://openalex.org/keywords/collision-prediction","display_name":"collision prediction","score":0.5320000052452087},{"id":"https://openalex.org/keywords/risk-prediction","display_name":"risk prediction","score":0.5630000233650208},{"id":"https://openalex.org/keywords/safety-violations","display_name":"safety violations","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5266000032424927},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3190999925136566},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprf71909.2026.00109","doi":"https://doi.org/10.1109/cvprf71909.2026.00109","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/cvprf71909.2026.00109","doi":"https://doi.org/10.1109/cvprf71909.2026.00109","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cvprf71909.2026.00109","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2740924709","https://openalex.org/W2925148167","https://openalex.org/W3035172746","https://openalex.org/W4292347911","https://openalex.org/W4386076400","https://openalex.org/W4390872423","https://openalex.org/W4399270650","https://openalex.org/W4403771534","https://openalex.org/W4404654834","https://openalex.org/W4405792757","https://openalex.org/W4407760074","https://openalex.org/W4409365971","https://openalex.org/W4409366191","https://openalex.org/W4413145448","https://openalex.org/W4413147287","https://openalex.org/W4414744621","https://openalex.org/W4414749964","https://openalex.org/W4415108483","https://openalex.org/W4415540607","https://openalex.org/W4415796242","https://openalex.org/W4415798424","https://openalex.org/W4416451800","https://openalex.org/W4416525310","https://openalex.org/W4416887510","https://openalex.org/W7124150836","https://openalex.org/W7133211372","https://openalex.org/W7133220049","https://openalex.org/W7160087193","https://openalex.org/W7160124948"],"related_works":["https://openalex.org/W7093093898","https://openalex.org/W2968807640","https://openalex.org/W6959822703","https://openalex.org/W7221025921","https://openalex.org/W7221016027","https://openalex.org/W2992718167","https://openalex.org/W4411361328","https://openalex.org/W3214115211","https://openalex.org/W2952056562","https://openalex.org/W7128284778"],"abstract_inverted_index":{"End-to-end":[0],"models":[1,49,60],"for":[2,51,76,173],"self-driving":[3],"hold":[4],"the":[5,47,64,120,135,163,166,171],"promise":[6],"of":[7,66,112,170,221],"learning":[8],"complex":[9],"behaviors":[10],"directly":[11],"from":[12,122],"sensor":[13],"data,":[14,58],"but":[15],"face":[16],"critical":[17,225],"challenges":[18],"in":[19,46,194,208,211],"safety":[20,209],"and":[21,25,115,140,231],"handling":[22],"long-tail":[23],"events,":[24],"Reinforcement":[26],"Learning":[27],"(RL)":[28],"offers":[29],"a":[30,39,42,74,99,109,123,128,183,201,205,217,224],"promising":[31],"path":[32],"to":[33,62,90,134,168,219],"overcome":[34],"these":[35,59],"limitations.":[36],"We":[37,95,142,176],"identify":[38],"fundamental":[40],"flaw:":[41],"deep-seated":[43],"\u201coptimistic":[44],"bias\u201d":[45],"world":[48],"used":[50,199],"RL.":[52],"Trained":[53],"exclusively":[54],"on":[55,182],"safe":[56,230],"expert":[57],"fail":[61],"predict":[63],"consequences":[65],"erroneous":[67],"actions.":[68,175],"To":[69],"address":[70],"this,":[71],"we":[72],"introduce":[73],"framework":[75],"posttraining":[77],"policy":[78],"refinement":[79],"built":[80],"around":[81],"an":[82,158],"Impartial":[83,146],"World":[84,147],"Model,":[85],"which":[86,106],"teaches":[87],"this":[88,97,145],"model":[89,121,190,218],"be":[91],"honest":[92],"about":[93],"danger.":[94],"achieve":[96],"with":[98],"novel":[100],"data":[101],"synthesis":[102],"pipeline,":[103],"Counterfactual":[104],"Synthesis,":[105],"systematically":[107],"generates":[108],"rich":[110],"curriculum":[111],"plausible":[113],"collisions":[114],"off-road":[116],"events.":[117],"This":[118],"transforms":[119],"passive":[124],"scene":[125],"completer":[126],"into":[127,149],"veridical":[129],"forecaster":[130],"that":[131,188,215],"remains":[132],"faithful":[133],"causal":[136],"link":[137],"between":[138],"actions":[139],"outcomes.":[141],"then":[143],"integrate":[144],"Model":[148],"our":[150,189],"closed-loop":[151],"RL":[152],"framework,":[153],"where":[154],"it":[155,203],"serves":[156],"as":[157,200],"internal":[159],"critic.":[160],"During":[161],"refinement,":[162],"agent":[164],"queries":[165],"critic":[167],"\u201cdream\u201d":[169],"outcomes":[172],"candidate":[174],"demonstrate":[177],"through":[178],"extensive":[179],"experiments,":[180],"including":[181],"new":[184],"Risk":[185],"Foreseeing":[186],"Benchmark,":[187],"significantly":[191],"outperforms":[192],"baselines":[193],"predicting":[195],"failures.":[196],"Consequently,":[197],"when":[198],"critic,":[202],"enables":[204],"substantial":[206],"reduction":[207],"violations":[210],"challenging":[212],"simulations,":[213],"proving":[214],"teaching":[216],"dream":[220],"danger":[222],"is":[223],"step":[226],"towards":[227],"building":[228],"truly":[229],"intelligent":[232],"autonomous":[233],"agents.":[234]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-09T00:00:00"}